<?xml version="1.0" encoding="utf-8"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:hal="http://hal.archives-ouvertes.fr/" xmlns:gml="http://www.opengis.net/gml/3.3/" xmlns:gmlce="http://www.opengis.net/gml/3.3/ce" version="1.1" xsi:schemaLocation="http://www.tei-c.org/ns/1.0 http://api.archives-ouvertes.fr/documents/aofr-sword.xsd">
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>HAL TEI export of hal-00722744</title>
      </titleStmt>
      <publicationStmt>
        <distributor>CCSD</distributor>
        <availability status="restricted">
          <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal</licence>
        </availability>
        <date when="2026-05-03T09:37:38+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">APRIL: Active Preference-learning based Reinforcement Learning</title>
            <author role="aut">
              <persName>
                <forename type="first">Riad</forename>
                <surname>Akrour</surname>
              </persName>
              <email type="md5">42ab7c998b1d7b20696503ae3547de94</email>
              <email type="domain">inria.fr</email>
              <idno type="idhal" notation="string">riad-akrour</idno>
              <idno type="idhal" notation="numeric">910562</idno>
              <idno type="halauthorid" notation="string">585406-910562</idno>
              <idno type="ARXIV">https://arxiv.org/a/akrour_r_1</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-8735-6960</idno>
              <affiliation ref="#struct-56057"/>
              <affiliation ref="#struct-2544"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Marc</forename>
                <surname>Schoenauer</surname>
              </persName>
              <email type="md5">6d215912b3c086d74cc5d8f7f3824951</email>
              <email type="domain">inria.fr</email>
              <idno type="idhal" notation="string">evomarc</idno>
              <idno type="idhal" notation="numeric">739309</idno>
              <idno type="halauthorid" notation="string">3534-739309</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-1450-6830</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=GrCk6WoAAAAJ&amp;hl=en</idno>
              <idno type="IDREF">https://www.idref.fr/057775575</idno>
              <orgName ref="#struct-300009"/>
              <affiliation ref="#struct-56057"/>
              <affiliation ref="#struct-2544"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Michèle</forename>
                <surname>Sebag</surname>
              </persName>
              <email type="md5">561bde41be5c447102107c78e945b69c</email>
              <email type="domain">lri.fr</email>
              <idno type="idhal" notation="numeric">1568820</idno>
              <idno type="halauthorid" notation="string">177819-1568820</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-8291-7706</idno>
              <idno type="IDREF">https://www.idref.fr/052538745</idno>
              <idno type="VIAF">https://viaf.org/viaf/272442549</idno>
              <idno type="ISNI">http://isni.org/isni/0000000383886590</idno>
              <orgName ref="#struct-441569"/>
              <affiliation ref="#struct-2544"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Marc</forename>
                <surname>Schoenauer</surname>
              </persName>
              <email type="md5">6d215912b3c086d74cc5d8f7f3824951</email>
              <email type="domain">inria.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2012-08-03 17:50:20</date>
              <date type="whenWritten">2012-02-08</date>
              <date type="whenModified">2025-11-14 13:04:03</date>
              <date type="whenReleased">2012-08-05 08:35:38</date>
              <date type="whenProduced">2012-09-24</date>
              <date type="whenEndEmbargoed">2012-08-03</date>
              <ref type="file" target="https://inria.hal.science/hal-00722744v1/document">
                <date notBefore="2012-08-03"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://inria.hal.science/hal-00722744v1/file/April_camera.pdf" id="file-722744-297114">
                <date notBefore="2012-08-03"/>
              </ref>
              <ref type="externalLink" target="http://arxiv.org/pdf/1208.0984"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="102427">
                <persName>
                  <forename>Marc</forename>
                  <surname>Schoenauer</surname>
                </persName>
                <email type="md5">6d215912b3c086d74cc5d8f7f3824951</email>
                <email type="domain">inria.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-00722744</idno>
            <idno type="halUri">https://inria.hal.science/hal-00722744</idno>
            <idno type="halBibtex">akrour:hal-00722744</idno>
            <idno type="halRefHtml">&lt;i&gt;ECML PKDD 2012&lt;/i&gt;, Sep 2012, Bristol, United Kingdom. pp.116-131</idno>
            <idno type="halRef">ECML PKDD 2012, Sep 2012, Bristol, United Kingdom. pp.116-131</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-722744-297114"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="EC-PARIS">Ecole Centrale Paris</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="INRIA">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="UNIV-PSUD">Université Paris Sud - Paris XI</idno>
            <idno type="stamp" n="INRIA-SACLAY" corresp="INRIA">INRIA Saclay - Ile de France</idno>
            <idno type="stamp" n="INRIA_TEST">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="TESTALAIN1">TESTALAIN1</idno>
            <idno type="stamp" n="UMR8623">Laboratoire de Recherche en Informatique</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="LRI-AO" corresp="UMR8623">Laboratoire de recherche en informatique. Équipe: Apprentissage et optimisation</idno>
            <idno type="stamp" n="UNIV-PARIS-SACLAY">Université Paris-Saclay</idno>
            <idno type="stamp" n="UNIV-PSUD-SACLAY" corresp="UNIV-PARIS-SACLAY">Université Paris Sud pour Paris Saclay</idno>
            <idno type="stamp" n="INRIA-300009">Inria 300009</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="invited" n="0">No</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
            <note type="proceedings" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">APRIL: Active Preference-learning based Reinforcement Learning</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Riad</forename>
                    <surname>Akrour</surname>
                  </persName>
                  <email type="md5">42ab7c998b1d7b20696503ae3547de94</email>
                  <email type="domain">inria.fr</email>
                  <idno type="idhal" notation="string">riad-akrour</idno>
                  <idno type="idhal" notation="numeric">910562</idno>
                  <idno type="halauthorid" notation="string">585406-910562</idno>
                  <idno type="ARXIV">https://arxiv.org/a/akrour_r_1</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-8735-6960</idno>
                  <affiliation ref="#struct-56057"/>
                  <affiliation ref="#struct-2544"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Marc</forename>
                    <surname>Schoenauer</surname>
                  </persName>
                  <email type="md5">6d215912b3c086d74cc5d8f7f3824951</email>
                  <email type="domain">inria.fr</email>
                  <idno type="idhal" notation="string">evomarc</idno>
                  <idno type="idhal" notation="numeric">739309</idno>
                  <idno type="halauthorid" notation="string">3534-739309</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-1450-6830</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=GrCk6WoAAAAJ&amp;hl=en</idno>
                  <idno type="IDREF">https://www.idref.fr/057775575</idno>
                  <orgName ref="#struct-300009"/>
                  <affiliation ref="#struct-56057"/>
                  <affiliation ref="#struct-2544"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Michèle</forename>
                    <surname>Sebag</surname>
                  </persName>
                  <email type="md5">561bde41be5c447102107c78e945b69c</email>
                  <email type="domain">lri.fr</email>
                  <idno type="idhal" notation="numeric">1568820</idno>
                  <idno type="halauthorid" notation="string">177819-1568820</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-8291-7706</idno>
                  <idno type="IDREF">https://www.idref.fr/052538745</idno>
                  <idno type="VIAF">https://viaf.org/viaf/272442549</idno>
                  <idno type="ISNI">http://isni.org/isni/0000000383886590</idno>
                  <orgName ref="#struct-441569"/>
                  <affiliation ref="#struct-2544"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>ECML PKDD 2012</title>
                  <date type="start">2012-09-24</date>
                  <date type="end">2012-09-28</date>
                  <settlement>Bristol</settlement>
                  <country key="GB">United Kingdom</country>
                </meeting>
                <editor>P. Flach et al.</editor>
                <imprint>
                  <publisher>Springer Verlag</publisher>
                  <biblScope unit="serie">Proc. ECML PKDD 2012, Part II</biblScope>
                  <biblScope unit="volume">7524</biblScope>
                  <biblScope unit="pp">116-131</biblScope>
                  <date type="datePub">2012-09-24</date>
                </imprint>
              </monogr>
              <idno type="arxiv">1208.0984</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">reinforcement learning</term>
                <term xml:lang="en">preference learning</term>
                <term xml:lang="en">interactive optimization</term>
                <term xml:lang="en">robotics</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-ai">Computer Science [cs]/Artificial Intelligence [cs.AI]</classCode>
              <classCode scheme="halTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halOldTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halTreeTypology" n="COMM">Conference papers</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>This paper focuses on reinforcement learning (RL) with limited prior knowledge. In the domain of swarm robotics for instance, the expert can hardly design a reward function or demonstrate the target behavior, forbidding the use of both standard RL and inverse reinforcement learning. Although with a limited expertise, the human expert is still often able to emit preferences and rank the agent demonstrations. Earlier work has presented an iterative preference-based RL framework: expert preferences are exploited to learn an approximate policy return, thus enabling the agent to achieve direct policy search. Iteratively, the agent selects a new candidate policy and demonstrates it; the expert ranks the new demonstration comparatively to the previous best one; the expert's ranking feedback enables the agent to refine the approximate policy return, and the process is iterated. In this paper, preference-based reinforcement learning is combined with active ranking in order to decrease the number of ranking queries to the expert needed to yield a satisfactory policy. Experiments on the mountain car and the cancer treatment testbeds witness that a couple of dozen rankings enable to learn a competent policy.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-56057" status="OLD">
          <idno type="RNSR">200418366A</idno>
          <orgName>Machine Learning and Optimisation</orgName>
          <orgName type="acronym">TAO</orgName>
          <date type="start">2004-11-04</date>
          <date type="end">2016-12-31</date>
          <desc>
            <address>
              <addrLine>DIGITEO Bat. Claude Shannon - Université de Paris-Sud, Bâtiment 660, 91190 Gif-sur-Yvette</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/equipes/tao</ref>
          </desc>
          <listRelation>
            <relation active="#struct-2544" type="direct"/>
            <relation active="#struct-92966" type="indirect"/>
            <relation active="#struct-411575" type="indirect"/>
            <relation name="UMR8623" active="#struct-441569" type="indirect"/>
            <relation active="#struct-118511" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-2544" status="OLD">
          <idno type="RNSR">199812948M</idno>
          <orgName>Laboratoire de Recherche en Informatique</orgName>
          <orgName type="acronym">LRI</orgName>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>LRI - Bâtiments 650-660 Université Paris-Sud 91405 Orsay Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.lri.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-92966" type="direct"/>
            <relation active="#struct-411575" type="direct"/>
            <relation name="UMR8623" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-92966" status="OLD">
          <idno type="ROR">https://ror.org/028rypz17</idno>
          <orgName>Université Paris-Sud - Paris 11</orgName>
          <orgName type="acronym">UP11</orgName>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>Bâtiment 300 - 91405 Orsay cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.u-psud.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-411575" status="VALID">
          <idno type="IdRef">184443237</idno>
          <idno type="ROR">https://ror.org/019tcpt25</idno>
          <orgName>CentraleSupélec</orgName>
          <desc>
            <address>
              <addrLine>3, rue Joliot Curie,Plateau de Moulon,91192 GIF-SUR-YVETTE Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.centralesupelec.fr</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-441569" status="VALID">
          <idno type="IdRef">02636817X</idno>
          <idno type="ISNI">0000000122597504</idno>
          <idno type="ROR">https://ror.org/02feahw73</idno>
          <orgName>Centre National de la Recherche Scientifique</orgName>
          <orgName type="acronym">CNRS</orgName>
          <date type="start">1939-10-19</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.cnrs.fr/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-118511" status="VALID">
          <idno type="RNSR">200818248E</idno>
          <idno type="ROR">https://ror.org/0315e5x55</idno>
          <orgName>Centre Inria de Saclay</orgName>
          <desc>
            <address>
              <addrLine>1 rue Honoré d'Estienne d'OrvesBâtiment Alan TuringCampus de l'École Polytechnique91120 Palaiseau</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/centre/saclay</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300009" status="VALID">
          <idno type="ROR">https://ror.org/02kvxyf05</idno>
          <orgName>Institut National de Recherche en Informatique et en Automatique</orgName>
          <orgName type="acronym">Inria</orgName>
          <desc>
            <address>
              <addrLine>Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/en/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>